Skip to main content

Table 2 Parameter estimates from the Weibull and Log-logistic frailty model with normal random effect for studying circumcision's effect on HR-HPV clearance.

From: Parametric frailty models for clustered data with arbitrary censoring: application to effect of male circumcision on HPV clearance

  Weibull Log-logistic
  Est. Std. Err. 95% C.I. LR P-value (2-sided) Est. Std. Err. 95% C.I. LR P-value (2-sided)
0.96 0.16 (0.63, 1.28)   1.78 0.28 (1.23, 2.33)  
-1.59 0.34 (-2.25, -0.93) < 0.0001 -1.30 0.17 (-1.63, -0.96) < 0.0001
0.42 0.23 (-0.02, 0.87) 0.04 0.45 0.22 (0.02, 0.89) 0.03
MSR2 1.56 0.35 (0.87, 2.24)   1.57 0.34 (0.90, 2.24)  
  1. The P-values were all obtained using likelihood ratio (LR) test.
  2. 1γ is a nuisance parameter, thus no P-value is presented as no hypothesis testing was performed. 2MSR: median survival time ratio (conditional on the random effect).
  3. 0Weibull model: MSR = exp( β 1); Log-logistic model: MSR = exp(β 1).
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us